© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 13016
    Prev
    Next
    INDEX
    Explanations

    words related to various types of animals, particularly mammals and reptiles

    oai_token-act-pair · gpt-3.5-turbo

    references to mammals and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stack
    -0.85
    acha
    -0.80
    Eng
    -0.65
    enburg
    -0.65
    JO
    -0.65
    oute
    -0.63
     Kou
    -0.63
     Coin
    -0.63
     Cra
    -0.63
     Ans
    -0.62
    POSITIVE LOGITS
     mammals
    3.79
     mammal
    3.37
     mammalian
    2.42
     primates
    2.33
     reptiles
    2.30
     rodents
    2.00
     verte
    1.84
     Mamm
    1.74
     rept
    1.73
     rodent
    1.73
    Activations Density 0.030%

    No Known Activations